Current Pubertal Development in Chinese Children and the Impact of Overnutrition, Lifestyle, and Perinatal Factors.

CONTEXT: Age of pubertal onset has been decreasing in many countries but there have been no data on pubertal development in Chinese children over the last decade. OBJECTIVE: The primary objective of the study was to evaluate the current status of sexual maturation in Chinese children and adolescents. Secondary objectives were to examine socioeconomic, lifestyle, and auxological associations with pubertal onset. METHODS: In this national, cross-sectional, community-based health survey, a multistage, stratified cluster random sampling method was used to select a nationally representative sample, consisting of 231 575 children and adolescents (123 232 boys and 108 343 girls) between 2017 and 2019. Growth parameters and pubertal staging were assessed by physical examination. RESULTS: Compared to 10 years previously, the median age of Tanner 2 breast development and menarche were similar at 9.65 years and 12.39 years respectively. However, male puberty occurred earlier with a median age of testicular volume ≥4 mL of 10.65 years. Pubertal onset did occur earlier at the extremes, with 3.3% of the girls with breast development at 6.5-6.99 years old, increasing to 5.8% by 7.5-7.99 years old. Early pubertal onset was also noted in boys, with a testicular volume ≥ 4 mL noted in 1.5% at 7.5-7.99 years, increasing to 3.5% at 8.5-8.99 years old. Obesity and overweight increased risk of developing earlier puberty relative to normal weight in both boys and girls. CONCLUSION: Over the past decade, pubertal development is occurring earlier in Chinese children. While the cause is multifactorial, overweight and obesity are associated with earlier puberty onset. The currently used normative pubertal data of precocious puberty may not be applicable to diagnose precocious puberty.

Diagnostic performance of convolutional neural network-based Tanner-Whitehouse 3 bone age assessment system.

BACKGROUND: Bone age can reflect the true growth and development status of a child; thus, it plays a critical role in evaluating growth and endocrine disorders. This study established and validated an optimized Tanner-Whitehouse 3 artificial intelligence (TW3-AI) bone age assessment (BAA) system based on a convolutional neural network (CNN). METHODS: A data set of 9,059 clinical radiographs of the left hand was obtained from the picture archives and communication systems (PACS) between January 2012 and December 2016. Among these, 8,005/9,059 (88%) samples were treated as the training set for model implementation, 804/9,059 (9%) samples as the validation set for parameters optimization, and the remaining 250/9,059 (3%) samples were used to verify the accuracy and reliability of the model compared to that of 4 experienced endocrinologists and 2 experienced radiologists. The overall variation of TW3-metacarpophalangeal, radius, ulna and short bones (RUS) and TW3-Carpal bone score, as well as each bone (13 RUS + 7 Carpal) between reviewers and the AI, were compared by Bland-Altman (BA) chart and Kappa test, respectively. Furthermore, the time consumption between the model and reviewers was also compared. RESULTS: The performance of TW3-AI model was highly consistent with the reviewers' overall estimation, and the root mean square (RMS) was 0.50 years. The accuracy of the BAA of the TW3-AI model was better than the estimate of the reviewers. Further analysis revealed that human interpretations of the male capitate, hamate, the first distal and fifth middle phalanx and female capitate, the trapezoid, and the third and fifth middle phalanx, were most inconsistent. The average image processing time was 1.5±0.2 s in the TW3-AI model, which was significantly shorter than manual interpretation. CONCLUSIONS: The diagnostic performance of CNN-based TW3 BAA was accurate and timesaving, and possesses better stability compared to diagnostics made by experienced experts.